Borrowing it
Nothing to install: this file belongs to chainstacklabs/polymarket-alpha-bot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chainstacklabs/polymarket-alpha-bot/main/.claude/skills/alphapoly-feature/SKILL.mdgit clone --depth 1 https://github.com/chainstacklabs/polymarket-alpha-botWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chainstacklabs/polymarket-alpha-bot/alphapoly-feature)<a href="https://agentmods.dev/skills/chainstacklabs/polymarket-alpha-bot/alphapoly-feature"><img src="https://agentmods.dev/badge/skills/chainstacklabs/polymarket-alpha-bot/alphapoly-feature/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chainstacklabs/polymarket-alpha-bot/alphapoly-feature"><img src="https://agentmods.dev/badge/skills/chainstacklabs/polymarket-alpha-bot/alphapoly-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00122 | $0.00633 |
| Opus 5.5 | $0.00049 | $0.00253 |
| Sonnet 5.5 | $0.00024 | $0.00127 |
| Haiku 4.5 | $0.00012 | $0.00063 |
Grade A, and why
Adding Alphapoly Features scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Adding Alphapoly Features
Key Conventions
- Backend: Python + FastAPI,
uvonly (never pip/conda),polars(never pandas) - Frontend: Next.js App Router, TypeScript
- Default LLM:
xiaomi/mimo-v2-flash:freevia OpenRouter - Run Python from:
backend/directory
Workflow
- Implement — follow patterns in neighboring files; see Common Touch Points below
- Lint —
make lintauto-fixes backend (ruff) and frontend (prettier + eslint) - Typecheck —
cd frontend && npm run typecheck(report-only; fix all errors before committing) - Verify — start
make devand manually test the feature works (check API responses, UI renders, WebSocket connects) - Commit —
type: description(feat/fix/refactor/chore)
Common Touch Points
New API endpoint:
- Add router:
backend/server/routers/<name>.py - Register in:
backend/server/main.py - Add TS types:
frontend/types/ - For complex logic, add a service in
backend/server/(followportfolio_service.pypattern)
New pipeline step:
- Add to:
backend/core/steps/ - Wire into:
backend/core/runner.py - For LLM/ML model access: use singletons in
backend/core/models.py
New domain feature (trading, wallet, positions):
- Add subdirectory:
backend/core/<domain>/withmanager.pyand/orservice.py - Add router:
backend/server/routers/<domain>.py - Follow existing pattern in
core/positions/,core/wallet/,core/trading/
New UI page:
- Add:
frontend/app/<page>/page.tsx - Link from:
frontend/components/Sidebar.tsx - API/tier config:
frontend/config/(api-config.ts,tier-config.ts)
WebSocket service:
- Backend:
backend/server/routers/(followportfolio_prices.pypattern) - Frontend hook:
frontend/hooks/ - Note:
frontend/server.jsproxies/api/*and/ws/*to the backend
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 49 lines · 122 tokens per session scan A 646ee2f4798c
Adding Alphapoly Features is a skill published in the GitHub repository chainstacklabs/polymarket-alpha-bot (184 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 122 tokens to every session and 633 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Adding Alphapoly Features compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Adding Alphapoly Featureschainstacklabs/polymarket-alpha-bot | Skill | 184 | 3mo ago | Apache-2.0 | A | 122 | Claude Code |
| langgraph-docslangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 62 | Claude Code, Codex |
| stripe-projectse2b-dev/E2B | Skill | 15k | yesterday | Apache-2.0 | A | 51 | Claude Code, Codex |
| calle-developerCALLE-AI/awesome-phone-call-agents | Skill | 112 | yesterday | MIT | A | 51 | Claude Code, Codex |
| python-patternsDDS-Solutions/AI-TadPole-OS | Skill | 8 | yesterday | MIT | A | 24 | Claude Code |
| cli-buildereddiebelaval/squire | Skill | 21 | 2mo ago | MIT | A | 47 | Claude Code, Codex |
| pn-python-scaffoldingperniemann/pnCore | Skill | 0 | 5d ago | MIT | A | 51 | Cursor |